The horizon of what repetitive tasks a computer can replace continues to expand due to artificial intelligence (AI) and the sub-field of deep learning (DL).
Artificial intelligence gives a device some form of human-like intelligence.
Deep learning is an AI technology that has made inroads into mimicking aspects of the human brain — giving a device the ability to process information for contextual analysis and action.
Researchers continue to develop self-teaching algorithms that enable deep learning AI applications like chatbots.
To understand deep learning better, we need to understand it as part of the AI evolution:
See more: Artificial Intelligence Market
The path to deep learning and reaching full AI
Taking machine learning farther
Within artificial intelligence, machine learning (ML) is a sub-field — and deep learning is an advanced sub-field of machine learning. In machine learning, a device is able to process and evaluate information beyond its programming based on context. An ML weakness stemming from polluted data sets comes from the fact that ML algorithms rely upon humans to supply the data: Humans categorize the information prior to training the algorithms or provide the algorithms with training feedback. Human subjectivity and biases subsequently creep into the algorithms.
Neural networks drive deep learning
Partly to eliminate human-based shortcomings in machine learning, researchers continue to try to create smarter ML algorithms. They design neural networks within ML that can learn on their own from raw, uncategorized data. Neural networks — the key to deep learning — incorporate algorithms based on mathematical formulas that add up weighted variables to generate a decision.
One example of a neural network algorithm is all of the possible variables a self-driving car considers when making the decision if it should proceed forward: is something in the way, is it dangerous to the car, is it dangerous to the passenger, etc. The weighting prioritizes the importance of the variables, such as placing passenger safety over car safety.
Deep learning extends ML algorithms to multiple layers of neural networks to make a decision tree of many layers of linked variables and related decisions. In the self-driving car example, moving forward would then lead to decisions regarding speed, the need to navigate obstacles, navigating to the destination, etc. Yet, those subsequent decisions may create feedback that forces the AI to reconsider earlier decisions and change them. Deep learning seeks to mimic the human brain in how we can learn by being taught and through multiple layers of near-simultaneous decision making.
AI use cases with deep learning
Deep learning promises to uncover information and patterns hidden from the human brain from within the sea of computer data.
AI with deep learning surrounds us. Apple’s Siri and Amazon’s Alexa try to interpret our speech and act as our personal assistants. Amazon and Netflix use AI to predict the next product, movie, or TV show we may want to enjoy. Many of the websites we visit for banking, health care, and e-commerce use AI chatbots to handle the initial stages of customer service.
Deep learning algorithms have been applied to:
- Customer service: Conversational AI incorporates natural language processing (NLP), call-center style decision trees, and other resources to provide the first level of customer service as chatbots and voicemail decision trees.
- Cybersecurity: AI analyzes log files, network information, and more to detect, report, and remediate malware and human attacks on IT systems.
- Financial services: Predictive analytics trade stocks, approve loans, flag potential fraud, and manage portfolios.
- Health care: Image-recognition AI reviews medical imaging to aid in medical analysis
- Law enforcement:
- Track payments and other financial transactions for signs of fraud, money laundering, and other crimes
- Extract patterns from voice, video, email and other evidence
- Analyze large amounts of data quickly
Artificial intelligence today
We do not currently have AI capable of thinking at the human level, but technologists continue to push the envelope of what AI can do. Algorithms for self-driving cars and medical diagnosis continue to be developed and refined.
So far, AI’s main challenges stem from unpredictability and bad training data:
- Biased AI judge (2019): To the great dismay of those trying to promote AI as unbiased, an AI algorithm designed to estimate recidivism, a key factor in sentencing, produced biased sentencing recommendations. Unfortunately, the AI learned from historical data which has racial and economic biases baked into the data; therefore, it continued to incorporate similar biases.
- Balls vs. bald heads (2020): The Caledonian Thistle FC trained AI for an automatic camera system to follow the ball on the soccer field. This worked well until a referee showed up with a shiny bald head and the AI followed the ref around the field instead.
AI consists of three general categories: artificial narrow intelligence (ANI) focuses on the completion of a specific task, such as playing chess or painting a car on an assembly line; artificial general intelligence (AGI) strives to reach a human’s level of intelligence; and artificial super intelligence (ASI) attempts to surpass humans. Neither of these last two categories exists, so all functional AI remains categorized as ANI.
Deep learning as a step
Deep learning continues to improve and deliver some results, but it cannot currently reach the higher sophistication levels needed to escape the artificial narrow intelligence category. As developers continue to add layers to the algorithms, AI will continue to assist with increasingly complex tasks and expand its utility. Even if human-like and superhuman intelligence through AI may be eluding us, deep learning continues to illustrate the increasing power of AI.